libqmi-glib,utils: assume non-printable UTF-8 is not expected

When a string comes in GSM7 instead of UTF-8, it may also happen that
it ends up being valid UTF-8 anyway. But, there may be cases that the
UTF-8 validity accepts non-printable characters, and that is something
we currently don't expect reported from the modem, so just go on and
assume that even if a string is valid UTF-8, it must contain all
printable UTF-8 characters, otherwise we'll attempt GSM-7 and UCS-2
decoding instead.

Fixes https://gitlab.freedesktop.org/mobile-broadband/ModemManager/issues/191

(cherry picked from commit b5c46e12332adc1084bde6e3652af67009f56e3c)

3 files changed, 34 insertions, 1 deletions

diff --git a/src/libqmi-glib/qmi-message.c b/src/libqmi-glib/qmi-message.c
index ca5756d..695ec7a 100644
--- a/src/libqmi-glib/qmi-message.c
+++ b/src/libqmi-glib/qmi-message.c
@@ -1325,7 +1325,7 @@ qmi_message_tlv_read_string (QmiMessage  *self,
      * but hey, the strings read using this method should all really be ASCII-7
      * and we're trying to do our best to overcome modem firmware problems...
      */
-    if (g_utf8_validate ((const gchar *)ptr, valid_string_length, NULL)) {
+    if (__qmi_string_utf8_validate_printable (ptr, valid_string_length)) {
         *out = g_malloc (valid_string_length + 1);
         memcpy (*out, ptr, valid_string_length);
         (*out)[valid_string_length] = '\0';
diff --git a/src/libqmi-glib/qmi-utils.c b/src/libqmi-glib/qmi-utils.c
index 8f40b5e..162db0a 100644
--- a/src/libqmi-glib/qmi-utils.c
+++ b/src/libqmi-glib/qmi-utils.c
@@ -120,6 +120,35 @@ __qmi_user_allowed (uid_t uid,
 }
 
 /*****************************************************************************/
+
+gboolean
+__qmi_string_utf8_validate_printable (const guint8 *utf8,
+                                      gsize         utf8_len)
+{
+    const gchar *p;
+    const gchar *init;
+
+    g_assert (utf8);
+    g_assert (utf8_len);
+
+    /* First check if valid UTF-8 */
+    init = (const gchar *)utf8;
+    if (!g_utf8_validate (init, utf8_len, NULL))
+        return FALSE;
+
+    /* Then check if contents are printable. If one is not,
+     * check fails. */
+    for (p = init; (gsize)(p - init) < utf8_len; p = g_utf8_next_char (p)) {
+        gunichar unichar;
+
+        unichar = g_utf8_get_char (p);
+        if (!g_unichar_isprint (unichar))
+            return FALSE;
+    }
+    return TRUE;
+}
+
+/*****************************************************************************/
 /* GSM 03.38 encoding conversion stuff, imported from ModemManager */
 
 #define GSM_DEF_ALPHABET_SIZE 128
diff --git a/src/libqmi-glib/qmi-utils.h b/src/libqmi-glib/qmi-utils.h
index 27cfe7e..7283101 100644
--- a/src/libqmi-glib/qmi-utils.h
+++ b/src/libqmi-glib/qmi-utils.h
@@ -86,6 +86,10 @@ gboolean __qmi_user_allowed (uid_t uid,
                              GError **error);
 
 G_GNUC_INTERNAL
+gboolean __qmi_string_utf8_validate_printable (const guint8 *utf8,
+                                               gsize         utf8_len);
+
+G_GNUC_INTERNAL
 gchar *__qmi_string_utf8_from_gsm7 (const guint8 *gsm,
                                     gsize         gsm_len);